https://github.com/hfooladi/alinemol
Exploring performance of machine learning model on out of distribution data in chemical domain
https://github.com/hfooladi/alinemol
cheminformatics generalization molecular-property-prediction out-of-distribution
Last synced: 3 months ago
JSON representation
Exploring performance of machine learning model on out of distribution data in chemical domain
- Host: GitHub
- URL: https://github.com/hfooladi/alinemol
- Owner: HFooladi
- License: mit
- Created: 2023-12-26T19:18:02.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-26T10:18:19.000Z (3 months ago)
- Last Synced: 2025-02-26T11:27:02.502Z (3 months ago)
- Topics: cheminformatics, generalization, molecular-property-prediction, out-of-distribution
- Language: Jupyter Notebook
- Homepage:
- Size: 16.9 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.cff
Awesome Lists containing this project
README
# ALineMol
Exploring performance of machine learning model on out of distribution data in chemical domain.
The goal is to explore and assess quantitavely the relationship between the performance of machine learning models on out-of-distribution (OOD) and the in-distribution (ID) test data.
## Installation
`ALineMol` can be installed using pip. First, create a new conda environment with the required packages. Then, clone this repository, and finally, install the repository using pip.
```bash
conda env create -f environment.yml
conda activate alinemol
pip install --no-deps -e .
```
## Development
### Tests
You can run tests locally with:
```bash
pytest
```
### Code style
We use `ruff` as a linter and formatter.
```bash
ruff check
ruff format
```
### Documentation
You can build and run documentation server with:
```bash
mkdocs serve
```
## Citation
If you find the models useful in your research, we ask that you cite the following paper: